All models

P-Video-Avatar

pruna/p-video-avatar
Pruna Video GenerationTalking HeadAvatar

Pruna's P-Video-Avatar generates talking-head videos from a single portrait image driven by a text script or audio file, with multiple voices, languages, and output resolutions.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "pruna/p-video-avatar",
    "audio": <string>,
    "image": <string>
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "pruna/p-video-avatar", "audio": "<string>", "image": "<string>"}'

Examples

Parameters

Input
audio string

URL of uploaded audio to drive speech. HTTP(S) URL or data URI. If both audio and voice_script are provided, audio takes priority. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.

disable_prompt_upsampling boolean required

When true, skip the prompt upsampler and pass the raw user prompt.

disable_safety_filter boolean required

Disable safety filter for prompts and input image.

image string required

Input portrait image (first frame). HTTP(S) URL or data URI. Supports jpg, jpeg, png, webp. Pass a public URL; to use a local file, upload it (free) via POST /v1/media (≤40MB) and pass the returned url.

negative_prompt string required

Mention what you do NOT want in the video. Disabled if empty.

resolution string required

Resolution of the video.

seed integer

Random seed for reproducible generation.

strength_negative_prompt number required

Strength of the negative prompt (0-4).

video_prompt string required

Optional prompt for the video.

voice string required

Voice for generated speech.

voice_language string required

Output language.

voice_prompt string required

Optional speaking style, tone, pacing or emotion instructions.

voice_script string required

Script for the person to say when no audio is uploaded.

Output
video: model output URL